CN108072664B - Appearance detection system and method - Google Patents
Appearance detection system and method Download PDFInfo
- Publication number
- CN108072664B CN108072664B CN201711481300.6A CN201711481300A CN108072664B CN 108072664 B CN108072664 B CN 108072664B CN 201711481300 A CN201711481300 A CN 201711481300A CN 108072664 B CN108072664 B CN 108072664B
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- appearance
- gray
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
The invention discloses an appearance detection system and method, wherein the system comprises a production line transmission unit, an image acquisition unit, a linear background light source and an image analysis processing unit, wherein: the assembly line conveying unit is used for conveying the object to be detected; the image acquisition unit is arranged above the production line conveying unit and used for acquiring a local image of the object to be detected; the linear background light source is arranged below the production line conveying unit, is opposite to the image acquisition unit and is used for calibrating the position of the object to be detected; and the image analysis processing unit is electrically connected with the image acquisition unit and is used for synthesizing the local image of the object to be detected into a complete appearance image and analyzing whether the surface of the object to be detected has defects or not according to the complete appearance image. The appearance detection system and the method provided by the invention can analyze and acquire whether the appearance of the object to be detected is qualified or not according to the local image of the object to be detected, and have the advantages of simple structure and high detection precision.
Description
Technical Field
The invention belongs to the technical field of visual inspection, and particularly relates to an appearance inspection system and method.
Background
At present, appearance detection of products is an important part of enterprise quality control. Most production enterprises can set appearance detection equipment on a production line, and the appearance of a product is ensured to meet the quality control requirement. The existing appearance detection technology generally adopts a high-pixel camera to shoot the whole product, and then whether the product appearance is qualified is analyzed by combining a software algorithm, so that the requirement on the camera is high, the price of the required camera is high, and the detection cost is high.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide an appearance detection system and method, which can adopt a camera with a lower specification to collect a local image of an object to be detected, analyze and acquire whether the appearance of the object to be detected is qualified or not, and have lower detection cost.
In order to achieve the above object, the present invention adopts the following technical solutions: an appearance inspection system comprising a pipeline transfer unit, an image acquisition unit, a linear background light source, and an image analysis processing unit, wherein:
the assembly line conveying unit is used for conveying the object to be detected;
the image acquisition unit is arranged above the production line conveying unit and used for acquiring a local image of the object to be detected;
the linear background light source is arranged below the production line conveying unit, is opposite to the image acquisition unit and is used for calibrating the position of the object to be detected;
and the image analysis processing unit is electrically connected with the image acquisition unit and is used for synthesizing the local image of the object to be detected into a complete appearance image and analyzing whether the surface of the object to be detected has defects or not according to the complete appearance image.
Further, the image acquisition unit comprises at least two electric coupling element cameras.
Further, the linear background light source is a linear LED backlight.
Further, the image analysis processing unit comprises an image splicing module, a position detection module and a hole detection module; wherein:
the image splicing module is used for synthesizing the local images of the object to be detected into a complete appearance image through a splicing algorithm;
the position detection module is used for acquiring the boundary of the object to be detected;
and the hole detection module is used for judging whether the surface of the object to be detected has hole defects or not.
Furthermore, the system also comprises a display control unit which is electrically connected with the image analysis processing unit and used for displaying the appearance analysis result of the object to be detected.
An appearance inspection method, comprising the steps of:
firstly, an object to be detected passes through an image acquisition unit and a linear background light source, and the image acquisition unit continuously acquires local images of the object to be detected;
secondly, the image analysis processing unit synthesizes the local images into a complete appearance image of the object to be detected according to an image splicing algorithm;
determining the boundary of the object to be detected in the complete appearance image according to the change of the gray value in the complete appearance image;
and step four, judging whether the surface of the object to be detected has hole defects or not according to the pixel gray value in the boundary of the object to be detected.
Further, in the third step, the step of determining the boundary of the object to be detected in the complete appearance image according to the change of the gray value in the complete appearance image includes:
converting the complete appearance image of the object to be detected into a gray image;
comparing the gray value of a pixel in the gray image with a preset first gray threshold value, and dividing the pixel in the gray image into a bright pixel and a dark pixel;
the bright pixels form a bright area, the dark pixels form a dark area, the boundary between the bright area and the dark area is the boundary of the object to be detected in the gray level image, and the dark area is the image of the object to be detected in the gray level image.
Further, the method for judging whether the surface of the object to be detected has the hole defect in the fourth step comprises the following steps:
comparing the gray value of the pixel in the dark area with a preset second gray threshold value, and finding out the pixel point larger than the second gray threshold value;
and judging whether the proportion of the adjacent pixel points larger than the second gray threshold value in the whole dark area pixel is larger than a preset proportion threshold value or not, and if so, marking the area occupied by the adjacent pixel points larger than the second gray threshold value as a defect hole.
Further, the method further comprises: and the display control unit displays the appearance detection result of the object to be detected.
The invention has the advantages that:
according to the appearance detection system and method provided by the invention, the local images of the object to be detected are obtained by the camera, then the local images are spliced into the complete image, the pixel gray level of the complete image is analyzed, and finally the appearance detection result of the object to be detected is obtained. Compared with the detection mode that the high-pixel camera is adopted to take the picture of the whole object to be detected in the prior art, the detection method has lower requirement on the camera, can reduce the detection cost, and can accurately detect whether the appearance of the object to be detected has defects or not by carrying out appearance detection in a gray level analysis mode.
Drawings
FIG. 1 is a schematic diagram of an appearance inspection system according to an embodiment of the present invention;
FIG. 2 is a schematic of bright and dark areas in a full appearance image according to one embodiment of the present invention;
fig. 3 is a flow chart of an appearance detection method according to an embodiment of the invention.
Detailed Description
The invention is described in detail below with reference to the figures and the embodiments.
Referring to fig. 1, in one embodiment of the present invention, an appearance inspection system includes a pipeline transfer unit 10, an image acquisition unit 20, a linear background light source 30, and an image analysis processing unit 40. Wherein:
a line conveying unit 10 for conveying the object 60 to be detected. Since the line type background light source 30 is installed below the line type conveying unit 10 for positioning the object 60 to be detected, the line type conveying unit 10 cannot completely block the emergent light of the line type background light source 30. The line unit 10 is preferably a roller conveyor belt arranged at a distance.
And the image acquisition unit 20 is arranged above the pipeline conveying unit 10 and is used for acquiring a local image of the object 60 to be detected. The image obtaining unit 20 may be a plurality of electric coupling element cameras 21, the plurality of cameras 21 are arranged above the pipeline conveying unit 10 in a linear arrangement, and each camera 21 respectively and continuously obtains a local image of the object 60 to be detected when the object 60 to be detected passes below the camera 21. The number of the cameras 21 can be set according to the width of the object to be detected, and preferably, the image acquisition unit 20 includes at least two electric coupling element cameras 21.
And a linear background light source 30 disposed below the line conveying unit 10 and opposite to the image acquiring unit 20. Preferably, the linear background light source 30 is a linear LED backlight to avoid the problem of flickering of the light source. When the object 60 to be detected passes through between the image acquisition unit 20 and the linear background light source 30, the object 60 to be detected blocks the emergent light of the linear background light source 30, so that the brightness of part of the object 60 to be detected is lower in the image acquired by the image acquisition unit 20, and the brightness of the part which is not blocked by the object 60 to be detected is higher. When the color image is converted into a gray image, the gray value of the part of the pixels with lower brightness is lower, and the gray value of the part of the pixels with higher brightness is higher.
And the image analysis processing unit 40 is electrically connected with the image acquisition unit 20 and is used for synthesizing the partial images of the object 60 to be detected into a complete appearance image and analyzing whether the surface of the object 60 to be detected has defects according to the complete appearance image. Specifically, the image analysis processing unit comprises the following modules:
and the image splicing module is used for synthesizing the local image of the object to be detected into a complete appearance image through a splicing algorithm. In the prior art, an image stitching algorithm generally identifies mutually overlapped parts in a plurality of local images, and then stitches different local images into a complete image according to the characteristics of the overlapped parts, and detailed description is omitted.
And the position detection module is used for acquiring the boundary of the object to be detected. Specifically, the position detection module converts the complete appearance image of the object to be detected into a gray image. And comparing the gray value of the pixel in the gray image with a preset first gray threshold value, wherein the pixel which is larger than the first gray threshold value is defined as a bright pixel, and the pixel which is smaller than or equal to the first gray threshold value is defined as a dark pixel. Referring to fig. 2, at this time, the bright pixel condensed region constitutes a bright area 101, and the dark pixel condensed region constitutes a dark area 102. The boundary between the bright area 101 and the dark area 102 is the boundary of the object to be detected in the gray image, and the dark area 102 is the image of the object to be detected in the gray image because the pixel gray value of the image of the object to be detected in the gray image is low. The first gray threshold value can be set according to different detection requirements.
And the hole detection module is used for judging whether the surface of the object to be detected has hole defects or not. Specifically, the hole detection module compares the pixel gray value in the dark area with a preset second gray threshold value to find out pixel points larger than the second gray threshold value, and holes may exist in the areas where the pixel points are located, so that light penetrates through the areas, and the gray value is higher than that of other normal areas. If the gray value of only one pixel point is abnormal, the result may be caused by measurement error, and it does not necessarily represent that a hole defect exists therein. And then, further judging whether the proportion of the adjacent pixel points larger than the second gray threshold value in the whole dark area pixel is larger than a preset proportion threshold value, and if so, marking the area occupied by the adjacent pixel points larger than the second gray threshold value as a defect hole area. The second gray level threshold value can be set according to the detection requirement, and the preset proportion threshold value is set according to the detection precision requirement.
In addition, in order to observe the detection result conveniently, the system may further include a display and control unit 50 electrically connected to the image analysis processing unit 40 for displaying the appearance analysis result of the object to be detected 60.
Referring to fig. 3, in another embodiment of the present invention, an appearance inspection method includes the steps of:
and S10, the object to be detected passes through the space between the image acquisition unit and the linear background light source, and the image acquisition unit continuously acquires the local images of the object to be detected.
And S20, the image analysis processing unit synthesizes the partial images into a complete appearance image of the object to be detected according to the image splicing algorithm.
And S30, determining the boundary of the object to be detected in the complete appearance image according to the change of the gray value in the complete appearance image. Specifically, the step of determining the boundary of the object to be detected in the complete appearance image includes:
s31, converting the complete appearance image of the object to be detected into a gray image;
s32, comparing the gray value of the pixel in the gray image with a preset first gray threshold value, and dividing the pixel in the gray image into a bright pixel and a dark pixel;
and S33, forming a bright area by the bright pixels and forming a dark area by the dark pixels, wherein the boundary between the bright area and the dark area is the boundary of the object to be detected in the gray level image, and the dark area is the image of the object to be detected in the gray level image.
And S40, judging whether the surface of the object to be detected has hole defects or not according to the pixel gray value in the boundary of the object to be detected. The method comprises the following specific steps:
s41, comparing the gray value of the pixel in the dark area with a preset second gray threshold value, and finding out the pixel point larger than the second gray threshold value;
and S42, judging whether the proportion of the adjacent pixel points larger than the second gray threshold value in the whole dark area pixel is larger than a preset proportion threshold value, and if so, marking the area occupied by the adjacent pixel points larger than the second gray threshold value as a defect hole.
In addition, the method further comprises S50, and the display control unit displays the appearance detection result of the object to be detected.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It should be understood by those skilled in the art that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by using equivalent alternatives or equivalent variations fall within the scope of the present invention.
Claims (5)
1. An appearance inspection system comprising a pipeline transfer unit, an image acquisition unit, a linear background light source, and an image analysis processing unit, wherein:
the assembly line conveying unit is used for conveying the object to be detected;
the image acquisition unit is arranged above the production line conveying unit and used for acquiring a local image of the object to be detected;
the linear background light source is arranged below the production line conveying unit, is opposite to the image acquisition unit and is used for calibrating the position of the object to be detected;
the image analysis processing unit is electrically connected with the image acquisition unit and is used for synthesizing the local image of the object to be detected into a complete appearance image and analyzing whether the surface of the object to be detected has defects or not according to the complete appearance image;
the image analysis processing unit comprises an image splicing module, a position detection module and a hole detection module;
wherein:
the image splicing module is used for synthesizing the local images of the object to be detected into a complete appearance image through a splicing algorithm;
the position detection module is used for acquiring the boundary of the object to be detected;
the hole detection module is used for judging whether the surface of the object to be detected has hole defects or not;
the appearance detection method of the appearance detection system comprises the following steps:
firstly, an object to be detected passes through an image acquisition unit and a linear background light source, and the image acquisition unit continuously acquires local images of the object to be detected;
secondly, the image analysis processing unit synthesizes the local images into a complete appearance image of the object to be detected according to an image splicing algorithm;
determining the boundary of the object to be detected in the complete appearance image according to the change of the gray value in the complete appearance image, wherein the step comprises the following steps of:
converting the complete appearance image of the object to be detected into a gray image;
comparing the gray value of a pixel in the gray image with a preset first gray threshold value, and dividing the pixel in the gray image into a bright pixel and a dark pixel;
the bright pixels form a bright area, the dark pixels form a dark area, the boundary of the bright area and the dark area is the boundary of the object to be detected in the gray level image, and the dark area is the image of the object to be detected in the gray level image;
step four, judging whether the surface of the object to be detected has a hole defect or not according to the pixel gray value in the boundary of the object to be detected;
comparing the gray value of the pixel in the dark area with a preset second gray threshold value, and finding out the pixel point larger than the second gray threshold value;
and judging whether the proportion of the adjacent pixel points larger than the second gray threshold value in the whole dark area pixel is larger than a preset proportion threshold value or not, and if so, marking the area occupied by the adjacent pixel points larger than the second gray threshold value as a defect hole.
2. The appearance inspection system of claim 1, wherein the image capture unit comprises at least two electric coupling element cameras.
3. The appearance inspection system according to claim 1, wherein the linear background light source is a linear LED backlight.
4. The appearance inspection system according to claim 1, further comprising a display and control unit electrically connected to the image analysis and processing unit for displaying the result of the appearance analysis of the object to be inspected.
5. The appearance inspection system of claim 1, wherein the method further comprises: and the display control unit displays the appearance detection result of the object to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711481300.6A CN108072664B (en) | 2017-12-29 | 2017-12-29 | Appearance detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711481300.6A CN108072664B (en) | 2017-12-29 | 2017-12-29 | Appearance detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108072664A CN108072664A (en) | 2018-05-25 |
| CN108072664B true CN108072664B (en) | 2020-12-08 |
Family
ID=62156120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711481300.6A Active CN108072664B (en) | 2017-12-29 | 2017-12-29 | Appearance detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108072664B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108982517A (en) * | 2018-07-25 | 2018-12-11 | 天津中车风电叶片工程有限公司 | A kind of Barcelona wood detection device |
| CN109584239B (en) * | 2018-12-13 | 2024-02-06 | 华南理工大学 | High-light object surface defect detection system and method based on reflected light |
| CN109632810A (en) * | 2019-01-03 | 2019-04-16 | 京东方科技集团股份有限公司 | Display panel crack detecting method and system |
| TWI793537B (en) * | 2021-02-26 | 2023-02-21 | 寶元數控股份有限公司 | Image acquisition method and device for plates |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002216109A (en) * | 2001-01-18 | 2002-08-02 | Sony Corp | Calibration method of image processor |
| CN101996405A (en) * | 2010-08-30 | 2011-03-30 | 中国科学院计算技术研究所 | Method and device for rapidly detecting and classifying defects of glass image |
| CN104111260A (en) * | 2014-07-09 | 2014-10-22 | 广州中国科学院沈阳自动化研究所分所 | Nondestructive ceramic detection device and detection method thereof |
| CN105424709A (en) * | 2015-11-20 | 2016-03-23 | 陕西科技大学 | Fruit surface defect detection method based on image marking |
| CN106204590A (en) * | 2016-07-11 | 2016-12-07 | 陕西科技大学 | A kind of paper defect testing method processed based on gray level image labelling |
-
2017
- 2017-12-29 CN CN201711481300.6A patent/CN108072664B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002216109A (en) * | 2001-01-18 | 2002-08-02 | Sony Corp | Calibration method of image processor |
| CN101996405A (en) * | 2010-08-30 | 2011-03-30 | 中国科学院计算技术研究所 | Method and device for rapidly detecting and classifying defects of glass image |
| CN104111260A (en) * | 2014-07-09 | 2014-10-22 | 广州中国科学院沈阳自动化研究所分所 | Nondestructive ceramic detection device and detection method thereof |
| CN105424709A (en) * | 2015-11-20 | 2016-03-23 | 陕西科技大学 | Fruit surface defect detection method based on image marking |
| CN106204590A (en) * | 2016-07-11 | 2016-12-07 | 陕西科技大学 | A kind of paper defect testing method processed based on gray level image labelling |
Non-Patent Citations (1)
| Title |
|---|
| 基于CT图像灰度水平的孔隙率计算及应用;王宇等;《水利学报》;20150331;第46卷(第3期);第357-365页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108072664A (en) | 2018-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108072664B (en) | Appearance detection system and method | |
| CN102413354B (en) | Automatic optical detection method, device and system of mobile phone camera module | |
| US9805458B2 (en) | Method and system for detecting defective pixels and screen imperfections of a mobile device | |
| TWI627854B (en) | Uneven spot inspection system, uneven spot inspection method and uneven spot inspection program | |
| CN104749184A (en) | Automatic optical detection method and automatic optical detection system | |
| TW201702586A (en) | Optical film defect detection method and system thereof | |
| CN103218961A (en) | Method and system for liquid crystal display (LCD) defect online detection | |
| EP3557216B1 (en) | Inspecting device, inspecting method, and program | |
| CN107144993B (en) | Display panel detection method and device | |
| CN103955080A (en) | Multi-camera liquid crystal screen defect detection and image collection device | |
| US20130100089A1 (en) | Newton ring mura detection system | |
| CN115917595A (en) | Surface defect detection system | |
| CN105304063A (en) | Image display device, image analysis method and image display method | |
| KR20190041009A (en) | Inspection device, inspection method and program | |
| CN106226033B (en) | Detect the method and device of transparent substrates transmitance | |
| KR20060052414A (en) | Method and apparatus for detecting flat panel display by vision model | |
| CN109712115B (en) | Automatic PCB detection method and system | |
| CN101556250A (en) | System and method thereof for checking product quality | |
| CN104359925A (en) | System for realizing automatic detection of electronic glass defects | |
| CN111474748A (en) | Machine vision inspection method and system for large-size L CD display module | |
| KR20140082333A (en) | Method and apparatus of inspecting mura of flat display | |
| KR102286470B1 (en) | LED Digital Signage Defect Detection system through Similarity Analysis of Original Image Information and Displayed Image Information | |
| CN115511791A (en) | Liquid crystal grating function detection method and system | |
| CN107024487B (en) | ITO conductive glass detection system and detection method thereof | |
| CN101178422B (en) | Character type illuminating device detecting method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 215000 No. 38 North Guandu Road, Yuexi Street, Wuzhong District, Suzhou City, Jiangsu Province Applicant after: SUZHOU DCCK MEASUREMENT AND CONTROL TECHNOLOGY CO., LTD. Address before: 215000 5th Floor, Block B3, Jinqiao Auto Parts Industrial Park, 1258 Jinfeng South Road, Wuzhong District, Suzhou City, Jiangsu Province Applicant before: SUZHOU DCCK MEASUREMENT AND CONTROL TECHNOLOGY CO., LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |